Trong Thang Pham

Hi! I'm Thang. Currently, I'm a PhD candidate at the University of Arkansas, Fayetteville under the supervision of Dr. Ngan Le. During my PhD, I research applying human eye gaze analysis to transform deep learning models based on human behavior. So far, I have contributed 7 papers to the medical field during my PhD. I used to work as a core R&D researcher at AIOZ Singapore, developing digital twin technologies including talking face generation and 3D human models for metaverse applications. Our team at AIOZ published two papers at CVPRW and CVPR. In summary, I have a strong publications in many top conferences, i.e. CVPR, ICCV, ACM MM, WACV, and ICRA, and journals, i.e. Image and Vision Computing (IVC) and Artificial Intelligence in Medicine (AIM) at Elsevier.

I genuinely love receiving emails and hearing from fellow researchers, students, engineers, and anyone interested in computer vision, medical AI, or related fields. Whether you want to discuss my research, share what you're working on, explore potential collaborations, or just chat about interesting ideas in our field, please don't hesitate to reach out at phamtrongthang123@gmail.com or tp030@uark.edu

CV / Google Scholar / Twitter / Github / Linkedin / Substack

Research Interests

I am interested in human behavior in professional settings. How do professionals behave during high-stake decision tasks? What cognitive goals drive their behavioral patterns? My work combines computer vision, interpretable AI, and deep learning to develop new models to capture and mimic human behavior in workplace environments. My current PhD work focuses on the medical/cardiology domain as the professional setting.

News

[July 2025] 🎉 Our paper "CT-ScanGaze: A Dataset and Baselines for 3D Volumetric Scanpath Modeling" has been accepted to ICCV 2025 as Highlight!
[July 2025] 🎉 Our paper "Interpreting Radiologist's Intention from Eye Movements in Chest X-ray Diagnosis" has been accepted to ACM MM 2025 as Oral!
[July 2025] 📝 Our paper "TolerantECG: A Foundation Model for Imperfect Electrocardiogram" has been accepted to ACM MM 2025!
[January 2025] 📝 Our paper "A2VIS: Amodal-Aware Approach to Video Instance Segmentation" has been accepted to Image and Vision Computing (IVC), Elsevier!
[November 2024] 📝 Our paper "ItpCtrl-AI: End-to-end interpretable and controllable artificial intelligence by modeling radiologists' intentions" has been accepted to Artificial Intelligence in Medicine (AIM), Elsevier!
[October 2024] 🎉 Our paper "GazeSearch: Radiology Findings Search Benchmark" has been accepted to WACV 2025 as Oral!
[September 2024] 📝 Our paper "FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation" has been accepted to ACCV 2024!

Selected Publications

	CT-ScanGaze: A Dataset and Baselines for 3D Volumetric Scanpath Modeling Trong Thang Pham, Akash Awasthi, Saba Khan, Esteban Duran Marti, Tien-Phat Nguyen, Khoa Vo, Minh Tran, Ngoc Son Nguyen, Cuong Tran Van, Yuki Ikebe, Anh Totti Nguyen, Anh Nguyen, Zhigang Deng, Carol C. Wu, Hien Van Nguyen, Ngan Le IEEE/CVF International Conference on Computer Vision (ICCV) (Highlight 2025) [Paper] [Code]
	Interpreting Radiologist's Intention from Eye Movements in Chest X-ray Diagnosis Trong Thang Pham, Anh Nguyen, Zhigang Deng, Carol C. Wu, Hien Van Nguyen, Ngan Le Proceedings of the ACM International Conference on Multimedia (ACMMM) (Oral 2025) [Paper] [Code]
	A2VIS: Amodal-Aware Approach to Video Instance Segmentation Trong Thang Pham, Minh Tran, Winston Bounsavy, Tri Nguyen, Ngan Le Image and Vision Computing, Elsevier, 2025 (Q1, IF 4.2) * same contribution [Paper]
	ItpCtrl-AI: End-to-end interpretable and controllable artificial intelligence by modeling radiologists' intentions Trong-Thang Pham, Jacob Brecheisen, Carol C. Wu, Hien Nguyen, Zhigang Deng, Donald Adjeroh, Gianfranco Doretto, Arabinda Choudhary, Ngan Le Artificial Intelligence in Medicine, Volume 160, February 2025 (Q1, IF 6.1) [Paper]
	GazeSearch: Radiology Findings Search Benchmark Trong Thang Pham,Tien-Phat Nguyen, Yuki Ikebe, Akash Awasthi, Zhigang Deng, Carol C. Wu, Hien Nguyen, Ngan Le IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (Oral 2025) [Paper] [Code]
	FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation Trong Thang Pham, Ngoc-Vuong Ho, Nhat-Tan Bui, Thinh Phan, Patel Brijesh, Donald Adjeroh, Gianfranco Doretto, Anh Nguyen, Carol C. Wu, Hien Nguyen, Ngan Le Asian Conference on Computer Vision (ACCV) (2024) [Paper] [Code]
	Decoding Radiologists Intense Focus for Accurate CXR Diagnoses: A Controllable and Interpretable AI System. Trong Thang Pham, Jacob Brecheisen, Anh Nguyen, Hien Nguyen, and Ngan Le IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024 [Paper] [Code]

Other Publications

	TolerantECG: A Foundation Model for Imperfect Electrocardiogram Huynh Nguyen Dang, Trong-Thang Pham, Ngan Le, Van Nguyen Proceedings of the ACM International Conference on Multimedia (ACMMM) 2025 [Paper]
	Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation. Yamazaki, Kashu, Taisei Hanyu, Khoa Vo, Trong Thang Pham, Minh Tran, Gianfranco Doretto, Anh Nguyen, and Ngan Le International Conference on Robotics and Automation (ICRA) 2024 [Paper] [Code]
	DNA: Deformable Neural Articulations Network for Template-Free Dynamic 3D Human Reconstruction From Monocular RGB-D Video. Vo, Khoa, Trong Thang Pham, Kashu Yamazaki, Minh Tran, and Ngan Le IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2023 [Paper]
	Music-Driven Group Choreography Le, Nhat, Trong Thang Pham, Tuong Do, Erman Tjiputra, Quang D. Tran, and Anh Nguyen IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023 [Paper] [Dataset]
	EmbryosFormer: Deformable Transformer and Collaborative Encoding-Decoding for Embryos Stage Development Classification. Nguyen, Tien-Phat, Trong Thang Pham, Tri Nguyen, Hieu Le, Dung Nguyen, Hau Lam, Phong Nguyen, Jennifer Fowler, Minh-Triet Tran, and Ngan Le IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023 [Paper]

Professional Services

- Reviewer at The Annual Conference on Neural Information Processing Systems (NeurIPS) 2025
- Reviewer at The ACM International Conference on Multimedia (MM) 2025
- Reviewer at IEEE Transaction of Image Processing
- Reviewer at CVPR 2024 & 2025
- Reviewer at ECCV 2024
- Reviewer at AAAI 2025
- Reviewer at WACV 2025
- Reviewer at ACCV 2024
- Reviewer Cv4animals Workshop at CVPR 2024

Teaching Assistant

- CSCE 5613: Introduction to Artificial Intelligence, University of Arkansas

Website template from Jon Barron.